pith:DIAXRENU
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
Robot action trajectories are mostly low-frequency, so diffusion policies need only two denoising steps for strong performance.
arxiv:2605.01581 v4 · 2026-05-02 · cs.RO
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{DIAXRENUE23EXZJJBKOJ7ULTR7}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
across RoboTwin2.0, Adroit, MetaWorld, and real-world tasks, HDP3 achieves state-of-the-art performance with fewer than 1% of the parameters of prior 3D diffusion-based policies and substantially lower inference latency.
That the low-frequency concentration observed in action trajectories and the derived error bound directly translate to sufficiency of exactly two denoising steps across the diverse tasks and action spaces tested, without hidden performance loss.
Hydra-DP3 achieves SOTA visuomotor performance with under 1% of prior 3D diffusion policy parameters by using frequency analysis to justify a lightweight decoder and two-step DDIM inference.
Receipt and verification
| First computed | 2026-06-01T01:02:41.158164Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
1a017891b426b64be5290a9c9fd1738ff2900ecba55c18f5d1269e75af571e53
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/DIAXRENUE23EXZJJBKOJ7ULTR7 \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 1a017891b426b64be5290a9c9fd1738ff2900ecba55c18f5d1269e75af571e53
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "0469e805ac3d77a3ba33a252121e21fdd7bc88b575caf1ae32d480e13d466ff3",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.RO",
"submitted_at": "2026-05-02T19:07:09Z",
"title_canon_sha256": "7a708af454819a9acd86f98df6920be10a4864f1e1c2dc8957e6aaa580104bea"
},
"schema_version": "1.0",
"source": {
"id": "2605.01581",
"kind": "arxiv",
"version": 4
}
}